2026-10-02T17:24:04.147096405Z (APIServer pid=1) INFO: 10.0.0.224:39518 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:04.246467388Z (APIServer pid=1) INFO: 10.0.0.224:39596 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:04.518966170Z (APIServer pid=1) INFO: 10.0.0.224:55628 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:24:04.635455770Z (APIServer pid=1) INFO: 10.0.0.224:39500 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:04.824132456Z (APIServer pid=1) INFO: 10.0.0.224:47094 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.289859329Z (APIServer pid=1) INFO: 10.0.0.224:37800 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.348268670Z (APIServer pid=1) INFO: 10.0.0.224:48096 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.445968670Z (APIServer pid=1) INFO: 10.0.0.224:47096 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.496529282Z (APIServer pid=1) INFO: 10.0.0.224:47108 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.505871629Z (APIServer pid=1) INFO: 10.0.0.224:47118 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:05.518124055Z (APIServer pid=1) INFO: 10.0.0.224:55628 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:24:06.105865844Z (APIServer pid=1) INFO: 10.0.0.224:52764 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:06.174122083Z (APIServer pid=1) INFO: 10.0.0.224:47122 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:06.518313497Z (APIServer pid=1) INFO: 10.0.0.224:55628 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:24:06.618364932Z (APIServer pid=1) INFO: 10.0.0.224:51270 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:06.730113619Z (APIServer pid=1) INFO: 10.0.0.224:39524 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:06.970873990Z (APIServer pid=1) INFO: 10.0.0.224:39486 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:07.519330509Z (APIServer pid=1) INFO: 10.0.0.224:55628 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:24:08.135165210Z (APIServer pid=1) INFO: 10.0.0.224:39656 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:08.519965199Z (APIServer pid=1) INFO: 10.0.0.224:55628 - "GET /metrics HTTP/1.1" 200 OK 2026-10-02T17:24:08.521992875Z (APIServer pid=1) INFO: 10.0.0.224:51712 - "POST /v1/chat/completions HTTP/1.1" 200 OK 2026-10-02T17:24:22.252050156Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] 2026-10-02T17:24:22.252097205Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] █ █ █▄ ▄█ 2026-10-02T17:24:22.252121070Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.29.0 2026-10-02T17:24:22.252124016Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] █▄█▀ █ █ █ █ model Qwen/Qwen2.5-7B-Instruct 2026-10-02T17:24:22.252126571Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀ 2026-10-02T17:24:22.252129445Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:347] 2026-10-02T17:24:22.260204992Z (APIServer pid=1) INFO 10-02 17:24:22 [api_utils.py:286] non-default args: {'model_tag': 'Qwen/Qwen2.5-7B-Instruct', 'host': '0.0.0.0', 'model': 'Qwen/Qwen2.5-7B-Instruct', 'revision': 'a09a35458c702b33eeacc393d103063234e8bc28', 'max_model_len': 1024, 'served_model_name': ['Qwen/Qwen2.5-7B-Instruct'], 'kv_cache_memory_bytes': 17179869184, 'enable_prefix_caching': False, 'cudagraph_metrics': True, 'max_num_seqs': 256, 'optimization_level': '2'} 2026-10-02T17:24:22.455643675Z (APIServer pid=1) INFO 10-02 17:24:22 [model.py:684] Resolved architecture: Qwen2ForCausalLM 2026-10-02T17:24:22.456121166Z (APIServer pid=1) INFO 10-02 17:24:22 [model.py:2021] Using max model len 1024 2026-10-02T17:24:22.459861954Z (APIServer pid=1) INFO 10-02 17:24:22 [kernel.py:369] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']) 2026-10-02T17:24:33.403643601Z (EngineCore pid=72) INFO 10-02 17:24:33 [core.py:123] Initializing a V1 LLM engine (v0.29.0) with config: model='Qwen/Qwen2.5-7B-Instruct', speculative_config=None, tokenizer='Qwen/Qwen2.5-7B-Instruct', skip_tokenizer_init=False, tokenizer_mode=auto, revision=a09a35458c702b33eeacc393d103063234e8bc28, tokenizer_revision=a09a35458c702b33eeacc393d103063234e8bc28, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=1024, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=None, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, per_request_spec_decode_metrics='none', kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=True, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False, jit_monitor_mode='warn', jit_monitor_verbose=False), seed=0, served_model_name=Qwen/Qwen2.5-7B-Instruct, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': , 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'ir_enable_torch_wrap': True, 'splitting_ops': ['vllm::unified_attention_with_output', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::qwen4_exp_compute_ple_ngram_ids', 'vllm::qwen4_exp_ple_short_conv', 'vllm::qwen4_exp_qsa_with_output', 'vllm::linear_attention', 'vllm::qwen_gdn_attention_core', 'vllm::qwen_gdn_attention_core_fused_norm_packed', 'vllm::gdn_attention_core_xpu', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::deepseek_v4_attention', 'vllm::hpc_rope_norm_forward', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': [], 'compile_ranges_endpoints': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': , 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False, 'enable_qk_norm_rope_fusion': False, 'fuse_rope_kvcache_cat_mla': False, 'fuse_act_padding': False, 'fuse_qk_norm_rope_kvcache': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': , 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['native'], fused_add_rms_norm=['native']), enable_flashinfer_autotune=True, enable_cutedsl_warmup=True, enable_jit_warmup=True, enable_bf16x3_router_gemm=False, moe_backend='auto', linear_backend='auto') 2026-10-02T17:24:35.769427176Z (EngineCore pid=72) :1297: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead. 2026-10-02T17:24:35.769609029Z (EngineCore pid=72) :1297: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead. 2026-10-02T17:24:36.387856882Z (EngineCore pid=72) INFO 10-02 17:24:36 [parallel_state.py:1775] world_size=1 rank=0 local_rank=0 distributed_init_method=file:///tmp/vllm_dist_1cfa1f52115946c9b034fe1c28975b69 backend=nccl 2026-10-02T17:24:36.396229849Z (EngineCore pid=72) INFO 10-02 17:24:36 [parallel_state.py:2119] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A 2026-10-02T17:24:36.396251009Z (EngineCore pid=72) INFO 10-02 17:24:36 [gpu_worker.py:429] Using V2 Model Runner 2026-10-02T17:24:37.264482595Z (EngineCore pid=72) INFO 10-02 17:24:37 [model_runner.py:382] Loading model from scratch... 2026-10-02T17:24:37.410004069Z (EngineCore pid=72) INFO 10-02 17:24:37 [cuda.py:492] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION']. 2026-10-02T17:24:37.410300077Z (EngineCore pid=72) INFO 10-02 17:24:37 [flash_attn.py:897] Using FlashAttention version 2 2026-10-02T17:24:37.779772027Z (EngineCore pid=72) INFO 10-02 17:24:37 [weight_utils.py:863] Filesystem type for checkpoints: EXT4. Checkpoint size: 14.19 GiB. Available RAM: 52.04 GiB. 2026-10-02T17:24:37.779950394Z (EngineCore pid=72) INFO 10-02 17:24:37 [weight_utils.py:886] Auto-prefetch is disabled because the filesystem (EXT4) is not a recognized network FS (NFS/Lustre). If you want to force prefetching, start vLLM with --safetensors-load-strategy=prefetch. 2026-10-02T17:24:37.780310433Z (EngineCore pid=72) Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00